基于数据映射算法的近邻存储方法研究

Abstract

随着互联网的高速发展，如何有效地存储海量数据以提供高效的查询效率是一项亟待解决的关键问题。然而，采用现有的例如Chord和P2P等分布式存储方案，面对高维、海量的存储数据时，数据存储规模和开销不断增加，造成存储效率以及数据查询效率不断降低。本文提出了基于数据映射算法的近邻存储方法。实验表明当进行相关性查询时，提高了查询准确率，同时显著降低了网络带宽。 With the high-speed development of the Internet, processing of high-dimensional and massive amounts of data for querying is a key challenge. However, for the traditional distributed storage scheme, such as the P2P network and Chord, the data storage capacity and the switch overheads from the nodes are increasing, thus decreasing the storage efficiency and data query efficiency continuously. In this article, a neighbor data storage approach based on data mapping algorithm is proposed. The experiment results show that the proposed method can improve the query accuracy rate and reduce network bandwidth through relevant query.